Automatic container portal crane control system

Abstract

The invention discloses an automatic container portal crane control system, and relates to the technical field of crane control. According to the automatic container portal crane control system, a data acquisition and identification module is used for acquiring feature data of to-be-stacked containers and performing identification and analysis to obtain each type of to-be-stacked containers, and an image analysis and processing module is used for acquiring image data and performing image analysis to obtain the to-be-stacked containers. The operation analysis and processing module is used for acquiring the operation state data of the container portal crane and carrying out data analysis, so as to obtain a plurality of grabbing control tracks for the container portal crane to grab the to-be-stacked containers to a preset target area; according to the method, the track control and adjustment measures are taken based on the operation stability indexes through the track control and adjustment module, so that reasonable stacking paths are planned for different types of containers, and the safety and the reliability of operation are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of crane control, and in particular to an automatic container gantry crane control system. Background Art

[0002] In modern port operations, automated container gantry cranes (ASCs) have been widely used in container stacking, handling and other related tasks in container yards. With the development of technology, container gantry cranes are gradually moving towards automation and intelligence to improve work efficiency, reduce human interference, and ensure operation safety. However, the existing automated container gantry crane control systems still face many challenges when performing precise operations. The path planning and trajectory control of container gantry cranes need to face a complex operating environment, which may lead to errors, collisions or trajectory deviations during operation, reducing operating efficiency.

[0003] Prior art, such as the automated container gantry crane control system disclosed in the patent application with announcement number: CN210558956U, includes: a central data processor for processing data information; a container truck position scanning system connected to the central data processor for scanning the position of the container truck; an indication system connected to the central data processor for indicating vehicle movement; a box placement system connected to the central data processor for controlling the spreader to place the box; a spreader position control system connected to the central data processor for monitoring the vertical position of the spreader and the deflection direction of the container; a container stacking scanning system connected to the central data processor for monitoring the stacking height of the container. Compared with the prior art, the automated container gantry crane control system provided by this application realizes fully automatic control of the gantry crane during container loading and unloading. It reduces the workload of staff, saves enterprise labor costs, and improves production efficiency.

[0004] Based on the above solution, it is found that the limitations of the existing technology include at least the following problems: the existing technology lacks in-depth recognition and analysis of container types and feature data, which may easily lead to inaccurate grasping, unreasonable path planning and other problems in the grabbing and stacking process of containers in actual operations, and when faced with complex or irregular stacking requirements, it is difficult to effectively optimize the operation trajectory of the spreader, resulting in low operating efficiency. Secondly, the existing technology lacks continuous analysis and dynamic adjustment of real-time operating status, which may easily lead to unstable operations in some non-standard environments, such as inconsistent container stacking heights, equipment failures, etc., thereby affecting operating efficiency and safety. Summary of the invention

[0005] In view of the deficiencies of the prior art, the present invention provides an automated container gantry crane control system, which solves the problem that the prior art is difficult to effectively optimize the running trajectory of the spreader when facing complex or irregular stacking requirements, resulting in low operating efficiency.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an automated container gantry crane control system, comprising: a data acquisition and recognition module, an image analysis and processing module, an operation analysis and processing module, and a trajectory control and adjustment module; the data acquisition and recognition module is used to acquire feature data of a plurality of containers to be stacked when stacking containers, and to perform recognition and analysis to obtain a plurality of containers to be stacked of a plurality of types; the image analysis and processing module is used to acquire image data of each container to be stacked of each type grabbed by the container gantry crane to be controlled between preset target areas, and to perform image analysis to obtain a plurality of paths between each container to be stacked of each type grabbed by the container gantry crane to be controlled between preset target areas The operation analysis and processing module is used to obtain in real time the operation status data of each grabbing control trajectory moving point in each grabbing control trajectory between the container gantry crane to be controlled grabbing each container to be stacked of each type to the preset target area, and perform data analysis to obtain the operation stability index of each grabbing control trajectory moving point in each grabbing control trajectory between the container gantry crane to be controlled grabbing each container to be stacked of each type to the preset target area; the trajectory control adjustment module is used to take trajectory control adjustment measures based on the operation stability index of each grabbing control trajectory moving point in each grabbing control trajectory between the container gantry crane to be controlled grabbing each container to be stacked of each type to the preset target area.

[0007] The present invention has the following beneficial effects: (1) The automated container gantry crane control system effectively improves the accuracy of container grabbing and stacking through container feature data recognition by the data acquisition and recognition module and path planning by the image analysis and processing module, and generates corresponding grabbing trajectories, thereby improving the overall operation accuracy and work efficiency when facing different types or irregular containers, thereby improving the efficiency of the entire yard operation.

[0008] (2) The automated container gantry crane control system can continuously monitor the trajectory control status of the container gantry crane by running real-time data collection and analysis of the analysis and processing module, especially real-time adjustment in complex operating environments, thereby reducing deviations during operation and effectively ensuring the smooth operation of the container crane in various environments, thereby reducing scheduling delays and downtime, and improving operational stability and safety.

[0009] (3) The automated container gantry crane control system uses an integrated data acquisition and recognition module, an image analysis and processing module, and a trajectory control and adjustment module to accurately identify different types of containers, generate an optimized grabbing path based on the recognition results, and adjust the stability of the operation trajectory based on real-time analysis, thereby ensuring that the consistency and accuracy of operations are significantly enhanced, thereby reducing the risk of problems occurring during operation and improving operational efficiency.

[0010] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 The present invention is a block diagram of an automated container gantry crane control system.

[0012] Figure 2 The present invention is a flowchart of the steps of obtaining a plurality of grabbing control trajectories for a container gantry crane to be controlled in an automated container gantry crane control system for grabbing each type of container to be stacked to a preset target area.

[0013] Figure 3 A flowchart of the steps of obtaining the operation stability index of each moving point of each grabbing control trajectory in each grabbing control trajectory of an automated container gantry crane control system of the present invention for grabbing each type of container to be stacked to a preset target area by the container gantry crane to be controlled. DETAILED DESCRIPTION

[0014] The overall idea of ​​the problem in the embodiment of this application is as follows: Firstly, the characteristic data of the containers to be stacked are acquired and analyzed through the data acquisition and recognition module, so as to identify different types of containers. Secondly, the image analysis and processing module is used to acquire the image data involved in the stacking process of the container gantry crane, and image analysis is performed to obtain the grabbing control trajectory of each container of each type. Finally, the operation analysis and processing module monitors the operation status data of each control trajectory moving point of the crane in the grabbing process in real time, analyzes and obtains the operation stability index of each trajectory point, and on this basis, the trajectory control adjustment module adjusts the trajectory in real time according to the stability index to ensure that the path and stability of the crane in actual operation are optimized.

[0015] See also Figure 1The embodiment of the present invention provides a technical solution: an automated container gantry crane control system, comprising the steps of: a data acquisition and recognition module, an image analysis and processing module, an operation analysis and processing module, and a trajectory control and adjustment module; the data acquisition and recognition module is used to acquire feature data of a plurality of containers to be stacked when stacking containers, and to perform recognition and analysis to obtain a plurality of containers to be stacked of a plurality of types (it should be noted that the container gantry crane stacks containers of the same type to the same preset target area); the image analysis and processing module is used to acquire image data between each container to be stacked of each type grabbed by the container gantry crane to be controlled and the preset target area, and to perform image analysis to obtain the ... The invention relates to a plurality of grabbing control trajectories for grabbing each container to be stacked to a preset target area; an operation analysis and processing module is used to obtain in real time the operation status data of each grabbing control trajectory moving point in each grabbing control trajectory between the container gantry crane to be controlled grabbing each container to be stacked of each type to the preset target area, and perform data analysis to obtain the operation stability index of each grabbing control trajectory moving point in each grabbing control trajectory between the container gantry crane to be controlled grabbing each container to be stacked of each type to the preset target area; a trajectory control adjustment module is used to take trajectory control adjustment measures based on the operation stability index of each grabbing control trajectory moving point in each grabbing control trajectory between the container gantry crane to be controlled grabbing each container to be stacked of each type to the preset target area.

[0016] The characteristic data include the aspect ratio (i.e. the ratio of the length to the width of the container), the height-to-width ratio (i.e. the ratio of the height to the width of the container), the volume value, and the weight value. The image data specifically includes the pixel value and two-dimensional coordinates of each pixel point. The operating status data includes the spreader acceleration value, the spreader angular velocity value, the spreader vibration amplitude index, the (crane) arm length value, the inclination angle value, the steel cable torque value, and the steel cable deformation value.

[0017] The two-dimensional coordinates take the upper left corner of the image as the origin, the horizontal axis of the image as the X-axis, and the vertical axis of the image as the Y-axis.

[0018] The acceleration value of the spreader can be obtained through the acceleration sensor.

[0019] The angular velocity of the spreader can be obtained through an angle sensor.

[0020] The spreader vibration amplitude index is the comprehensive vibration amplitude of the spreader in the horizontal, longitudinal and vertical directions. The spreader vibration amplitude index can be obtained by weighting the vibration amplitudes of the spreader in the horizontal, longitudinal and vertical directions, and the processing result is the spreader vibration amplitude index.

[0021] The arm length value is the arm length value of the crane at the moving point of the grab control trajectory, which can be obtained by a laser rangefinder.

[0022] The tilt angle value is the tilt angle of the crane base relative to the ground, which can be obtained by the tilt sensor.

[0023] The torque value of the steel cable is the rotational moment acting on the steel cable, that is, the reaction force of the steel cable in the torsional direction when it is subjected to force, which can be obtained by a torque sensor.

[0024] The deformation value of the steel cable is the degree of deformation (i.e., the deformation amount) of the steel cable when subjected to external force, which can be obtained through a strain sensor.

[0025] Specifically, the specific steps of obtaining several types of containers to be stacked are as follows: normalizing the length-to-width ratio, height-to-width ratio, volume value, and weight value of each container to be stacked (i.e., removing the unit); comprehensively analyzing the length-to-width ratio, height-to-width ratio, volume value, and weight value of each container to be stacked after the normalization process to obtain a characteristic index of each container to be stacked; and judging and analyzing the characteristic index of each container to be stacked with a preset characteristic index threshold range to obtain several types of containers to be stacked.

[0026] The specific process of the judgment and analysis is as follows: if the characteristic index of the container to be stacked is lower than the preset characteristic index threshold interval (minimum value), the container to be stacked is marked as the first type (of the container to be stacked); if the characteristic index of the container to be stacked is within the preset characteristic index threshold interval, the container to be stacked is marked as the second type (of the container to be stacked); if the characteristic index of the container to be stacked is higher than the preset characteristic index threshold interval (maximum value), the container to be stacked is marked as the third type (of the container to be stacked); and statistical analysis is performed based on the above results to obtain several types of containers to be stacked.

[0027] The specific formula for calculating the characteristic index of each container to be stacked is as follows: ;in, is the characteristic index of the jth container to be stacked, is the normalized length-to-width ratio, height-to-width ratio, volume, and weight of the jth container to be stacked, α1 is the length-to-width ratio coefficient stored in the database, is the height-to-width ratio of the jth container to be stacked after normalization, α2 is the height-to-width ratio coefficient stored in the database, is the volume value of the jth container to be stacked after normalization, α3 is the volume coefficient stored in the database, is the weight value of the jth container to be stacked after normalization, α4 ​​is the weight coefficient stored in the database, α5 is the interaction coefficient stored in the database, j = 1, 2, 3, …, j0, j0 is the number of containers to be stacked.

[0028] It should be explained that the formula This item is used to adjust the superposition effect of the normalized length-to-width ratio, height-to-width ratio, volume value, and weight value of the containers to be stacked to prevent the characteristic index from being too high or too low.

[0029] α1, α2, α3, α4, and α5 can be obtained through the following steps: using historical data, combined with the normalized length-to-width ratio, height-to-width ratio, volume value, and weight value of the containers to be stacked, statistical regression analysis is performed to quantify the specific impact of each factor on the characteristic index, thereby fitting the initial weight value; secondly, using the sensitivity analysis method, the value range of each coefficient is adjusted to observe its impact on the characteristic index to ensure the stability and rationality of the model; based on the actual situation, the preliminary fitted coefficients are corrected and optimized to finally determine the coefficient value applicable to the container.

[0030] The specific implementation example of calculating the characteristic index of the first container to be stacked is as follows, and the following data is available: The length-to-width ratio of the first container to be stacked is: 2.51.

[0031] The height-to-width ratio of the first container to be stacked is: 1.02.

[0032] The volume of the first container to be stacked is (unit: m 3 ):33.

[0033] The weight of the first container to be stacked is (in tons): 24.

[0034] And normalize the above data to get: The normalized length-to-width ratio of the first container to be stacked is: 0.45.

[0035] The height-to-width ratio of the first container to be stacked after normalization is: 0.49.

[0036] The volume value of the first container to be stacked after normalization is: 0.75.

[0037] The normalized weight value of the first container to be stacked is: 0.62.

[0038] And the aspect ratio coefficient stored in the database is approximately: 0.35.

[0039] The aspect ratio factor stored in the database is approximately: 0.41.

[0040] The volume factor stored in the database is approximately: 0.61.

[0041] The weight factor stored in the database is approximately: 0.57.

[0042] The interaction coefficient stored in the database is approximately: 4.89.

[0043] Substituting the above data into the specific formula of the characteristic index of each container to be stacked, we get: The characteristic index of the first container to be stacked = 0.45 0.35 ×0.49 0.41 ×0.75 0.61 ×0.62 0.57 / ×0.45×0.49×0.75×0.62≈0.72.

[0044] In this implementation scheme, the overall characteristics of the container are accurately evaluated by normalizing the length-to-width ratio, height-to-width ratio, volume value, and weight value of each container to be stacked, and the regression analysis and sensitivity analysis of historical data are combined to quantify the impact of different factors on container stacking, ensure that the classification of containers is more refined and scientific, and provide an accurate basis for subsequent stacking planning, path selection, and operation adjustment, thereby improving the intelligence and accuracy of the system. Secondly, by obtaining the characteristic index of each container and classifying the types based on it, the stacking position of the container can be arranged more reasonably. Different types of containers will be arranged to the most suitable stacking area according to their characteristics, thereby effectively reducing the interference that may occur during the operation of the container, avoiding space waste and mechanical arm interference caused by unreasonable container stacking, thereby improving the efficiency and safety of the crane operation. Finally, the calculation of the characteristic index and the coefficient adjustment steps can dynamically adjust the coefficients according to different situations through sensitivity analysis and regression optimization, so that the container stacking system has stronger adaptability and stability, and can maintain an efficient working state in a complex and changeable yard environment, thereby reducing the risk of human operation errors.

[0045] Specifically, Figure 2As shown, the specific steps of obtaining a plurality of grabbing control trajectories for the container gantry crane to be controlled to grab each container to be stacked of each type to a preset target area are as follows: the pixel value of each pixel point between the container gantry crane to be controlled to grab each container to be stacked of each type to the preset target area is respectively input into the pre-trained recognition model for recognition processing to obtain a plurality of obstacle areas between the container gantry crane to be controlled to grab each container to be stacked of each type to the preset target area; the two-dimensional coordinates of each obstacle pixel point in each obstacle area between the container gantry crane to be controlled to grab each container to be stacked of each type to the preset target area are analyzed by median value to obtain the two-dimensional coordinates of each obstacle area between the container gantry crane to be controlled to grab each container to be stacked of each type to the preset target area, and the coordinate conversion processing is performed to obtain the three-dimensional position coordinates of the obstacles of each obstacle area between the container gantry crane to be controlled to grab each container to be stacked of each type to the preset target area; the three-dimensional lifting position coordinates of the container gantry crane to be controlled and the target area of ​​each container to be stacked of each type are obtained. The three-dimensional position coordinates are marked, and interpolation analysis is performed to obtain the three-dimensional position coordinates of several potential moving points between the container gantry crane to be controlled to grab each container to be stacked of each type and the preset target area (it should be noted that the three-dimensional position coordinates at this time are the predicted positions of the container gantry crane moving to the potential moving points); the three-dimensional position coordinates of the lifting of each potential moving point between the container gantry crane to be controlled to grab each container to be stacked of each type and the preset target area are respectively analyzed with the three-dimensional position coordinates of the obstacles in each obstacle area and the preset safe moving distance of the container gantry crane (it should be noted that the safe moving distance is the radius of the range of safe movement of the container gantry crane) to obtain the reliability index of each potential moving point between the container gantry crane to be controlled to grab each container to be stacked of each type and the preset target area; and the reliability index of each potential moving point between the container gantry crane to be controlled to grab each container to be stacked of each type and the preset target area is comprehensively analyzed to obtain several grab control trajectories between the container gantry crane to be controlled to grab each container to be stacked of each type and the preset target area.

[0046] Among them, the three-dimensional position coordinates of the crane and the three-dimensional position coordinates of the obstacle both take the center point of the horizontal plane of the site as the origin, the horizontal transverse direction along the site as the X-axis, the horizontal longitudinal direction along the site as the Y-axis, and the height direction along the site as the Z-axis.

[0047] The interpolation analysis uses the interpolation method, that is, estimating the value at the unknown position through the known data points, and the spline interpolation is adopted in this embodiment. The spline interpolation is an interpolation method that uses piecewise polynomials to smooth over data points. It uses cubic polynomials to interpolate, and the derivative (rate of change) between every two adjacent data points is continuous.

[0048] The specific formula for calculating the reliability index of each potential moving point between the container gantry crane to be controlled to grab each type of each container to be stacked to the preset target area is as follows: ; Among them, KxZ ijg is the reliability index of the container gantry crane to be controlled to grab the jth container to be stacked of the i-th type to the g-th potential moving point between the preset target area, (Xw ijg , Y ijg , Zw ijg ) is the lifting three-dimensional position coordinate of the g-th potential moving point between the container gantry crane to grab the j-th container to be stacked of the i-th type and the preset target area, (Xq ijh , Yq ijh , Zq ijh ) is the obstacle 3D position coordinate of the h-th obstacle area between the container gantry crane to be controlled to grab the j-th container to be stacked of the ith type and the preset target area, AyL is the preset safe moving distance of the container gantry crane, i=1,2,3,…,i0, i0 is the number of types, j=1,2,3,…,j0, j0 is the number of containers to be stacked, g=1,2,3,…,g0, g0 is the number of potential moving points, and h=1,2,3,…,h0, h0 is the number of obstacle areas.

[0049] In this implementation scheme, reliability analysis is performed on each potential moving point to obtain the safest and most effective grasping trajectory, avoid collisions and wrong paths, and thus improve the working efficiency and accuracy of the container gantry crane. Secondly, the obstacle area is identified and analyzed, and a comprehensive analysis is performed in combination with the safe moving distance, so as to effectively avoid collisions between the crane and obstacles during operation, reduce equipment damage and safety hazards, and calculate the position of the potential moving point through interpolation analysis, so as to flexibly respond to changes in the container yard, optimize path planning and improve operating efficiency. At the same time, through median analysis and coordinate transformation, the three-dimensional position coordinates of all obstacles can be accurately determined, so as to ensure the reliability and accuracy of the operation. Finally, a comprehensive analysis is performed on the reliability index of the potential moving point to ensure that the container gantry crane always remains within a safe working range during operation, thereby preventing safety accidents caused by operational errors and helping to improve the overall efficiency and stability of the crane operation.

[0050] Specifically, the recognition model is a convolutional neural network model, which includes an input layer, a convolutional layer, an activation layer, a pooling layer, a fully connected layer, and an output layer. The specific steps of obtaining the obstacle areas between the preset target areas when the container gantry crane to be controlled grabs each type of container to be stacked are as follows: in the input layer of the convolutional neural network model, receiving the pixel value of each pixel point between the preset target areas when the container gantry crane to be controlled grabs each type of container to be stacked; in the convolutional layer of the convolutional neural network model, performing feature extraction processing on the pixel value of each pixel point between the preset target areas when the container gantry crane to be controlled grabs each type of container to be stacked (that is, automatically extracting local features in the image through convolution operations, such as edges, textures, shapes, etc., and the convolutional layer uses multiple convolution kernels to scan the input image to generate a feature map), and obtaining the feature map between the preset target areas when the controlled container gantry crane grabs each type of container to be stacked; in the activation layer of the convolutional neural network model, performing feature extraction processing on the pixel value of each pixel point between the preset target areas when the controlled container gantry crane grabs each type of container to be stacked The feature maps between the preset target areas are processed by nonlinear transformation (i.e., activation functions are used to help the network introduce nonlinear features, and the commonly used activation function is ReLU); in the pooling layer of the convolutional neural network model, the feature maps between the preset target areas where the controlled container gantry crane grabs each type of container to be stacked after the nonlinear transformation are processed are processed by dimensionality reduction (i.e., the feature maps are downsampled to reduce the size of the feature maps and extract the most important feature information. The commonly used operation of the pooling layer is maximum pooling, which selects the largest value in each pooling area to represent the area), and the reduced-dimensional feature maps between the preset target areas where the controlled container gantry crane grabs each type of container to be stacked are obtained; in the fully connected layer of the convolutional neural network model, the reduced-dimensional feature maps between the preset target areas where the controlled container gantry crane grabs each type of container to be stacked are flattened (after the convolutional layer and the pooling layer are processed, the feature maps usually have a higher dimension, usually a three-dimensional array, such as height × width × number of channels. In order to be able to perform further analysis and processing in the fully connected layer, these three-dimensional feature maps need to be flattened into a one-dimensional vector);In the output layer of the convolutional neural network model, the flattened controlled container gantry crane grabs each type of container to be stacked to the preset target area, and the reduced dimension feature map is subjected to contour recognition analysis (i.e., each pixel is classified to determine whether it belongs to the target contour area, and the Sigmoid activation function is used to map the predicted value of each pixel point to the range of [0,1]. By setting the threshold, a binary image is output, and a value of 1 indicates that the pixel belongs to the target contour, and a value of 0 indicates that the pixel is the background. These contour areas are the target areas finally extracted). The controlled container gantry crane grabs each type of container to be stacked to several obstacle areas between the preset target areas. ;

[0051] Among them, the pre-training steps of the convolutional neural network model are as follows: Several groups of image data are obtained, and each group of image data is preprocessed, and each group of image data after preprocessing is divided into a training set and a validation set, and the convolutional neural network is initialized, that is, the weights and biases in the network are initialized to ensure that the network can effectively learn features.

[0052] Perform training based on the image training set, that is, the number of training cycles. Set the number of training cycles (for example, train 50 times).

[0053] And the processing steps of each training cycle are as follows: Forward propagation: Each batch of images is input into the CNN network, and features are gradually extracted and contour maps are generated through convolutional layers, activation layers, pooling layers, deconvolution layers, etc.

[0054] Loss function: Calculates the error between the predicted image and the true label, such as the cross entropy loss function.

[0055] Backpropagation: The gradient in the network is calculated according to the loss function and the model parameters are updated through an optimizer (such as the Adam optimizer).

[0056] After each training cycle, evaluation analysis is performed based on the image validation set.

[0057] Perform a forward pass using the images in the validation set and calculate the loss.

[0058] Parameter adjustment: Based on the evaluation results, if the loss on the validation set does not decrease or the accuracy does not improve, you may need to adjust the network's hyperparameters (such as learning rate, network structure, etc.).

[0059] When the training is completed and the loss and accuracy on the validation set reach the expected standards, the training process ends and a trained network model is obtained.

[0060] Final model: This model is able to accurately extract the outline of the target from the image and can be used for subsequent target recognition, target tracking and other tasks.

[0061] In this implementation scheme, the convolutional neural network can automatically extract local features such as edges, shapes, textures, etc. from the image through the convolution layer and the pooling layer without manually extracting these features, thereby effectively improving the efficiency of image recognition and being able to adapt to different types of containers and environmental changes. By introducing nonlinear features through activation functions (such as ReLU), the convolutional neural network can better simulate and learn complex image patterns, which is crucial for the recognition of complex shapes and obstacles of containers. Secondly, by performing contour recognition analysis in the output layer and using the Sigmoid activation function to map the value of each pixel to 0 or 1, accurate obstacle area segmentation is achieved, which helps to accurately identify obstacle areas in the container yard, thereby ensuring that the crane can avoid these areas and reduce the risk of collision. At the same time, through the pre-training process, the convolutional neural network can automatically learn to extract the optimal features from the input image, and during the training process, the network can optimize the weights and biases through the back-propagation algorithm, so that the model can gradually improve the recognition accuracy of obstacles. Finally, the network can be trained according to the environment of different container yards, thereby ensuring good adaptability in a variety of work scenarios and effective use of computing resources.

[0062] Specifically, the specific steps of comprehensively analyzing the reliability index of each potential moving point between each type of each container to be stacked and the preset target area by the container gantry crane to be controlled are as follows: the reliability index of each potential moving point between each type of each container to be stacked and the preset target area by the container gantry crane to be controlled is compared and analyzed with the preset reliability index threshold value; if the reliability index of each potential moving point between each type of each container to be stacked and the preset target area by the container gantry crane to be controlled is lower than or equal to the preset reliability index threshold value, then the potential moving point is not marked; if the reliability index of each potential moving point between each type of each container to be stacked and the preset target area by the container gantry crane to be controlled is lower than or equal to the preset reliability index threshold value, then the potential moving point is not marked; if the reliability index of each potential moving point between each type of each container to be stacked and the preset target area by the container gantry crane to be controlled is lower than or equal to the preset reliability index threshold value, then the potential moving point is not marked. If the reliability index of each potential moving point between grabbing each container to be stacked of a certain type and a preset target area is higher than a preset reliability index threshold, the potential moving point is marked as a grabbing control trajectory moving point, and statistical analysis is performed to obtain a number of grabbing control trajectory moving points between grabbing each container to be stacked of a certain type by the container gantry crane to be controlled and the preset target area; and each grabbing control trajectory moving point between grabbing each container to be stacked of a certain type by the container gantry crane to be controlled and the preset target area is smoothed to obtain a number of grabbing control trajectories between grabbing each container to be stacked of a certain type by the container gantry crane to be controlled and the preset target area.

[0063] In this implementation scheme, by comparing the reliability index of each potential moving point with a preset threshold, the moving points that do not meet the safety standards are effectively screened out, thereby ensuring that only potential moving points with a higher reliability index are selected as components of the grasping control trajectory, thereby reducing the risk of collision caused by obstacles or other unsafe factors. Secondly, by screening the potential moving points, only those points that meet the high reliability requirements are marked and processed, avoiding further calculation and processing of invalid or low reliability points, thereby improving calculation efficiency and reducing unnecessary resource consumption. At the same time, by statistically analyzing the potential moving points with higher reliability, a more accurate and effective grasping trajectory is determined, so that the crane can avoid unstable or unsafe paths when performing tasks, thereby improving the accuracy and reliability of grasping. Then, the moving points of the grasping control trajectory are smoothed, which can reduce sharp turns or unnecessary movements in the trajectory, making the movement of the crane smoother and improving the stability of task execution. Finally, by marking the moving points that meet the conditions and performing statistical and smoothing processing, the safety of the operation is improved, thereby avoiding performing tasks under unsafe conditions, thereby ensuring the reliability of container gantry cranes in various complex environments.

[0064] Specifically, Figure 3As shown, the specific steps of obtaining the operation stability index of each grabbing control trajectory moving point in each grabbing control trajectory of the container gantry crane to be controlled to grab each type of each container to be stacked to a preset target area are as follows: obtain the spreader acceleration reference value, spreader angular velocity reference value, spreader vibration amplitude reference index, arm length reference value, tilt angle reference value, steel cable torque reference value, and steel cable deformation reference value of the container gantry crane to be controlled; comprehensively analyze the spreader acceleration reference value, spreader angular velocity reference value, and spreader vibration amplitude reference index of the container gantry crane to be controlled and the spreader acceleration value, spreader angular velocity value, and spreader vibration amplitude index of each grabbing control trajectory moving point in each grabbing control trajectory between grabbing each type of each container to be stacked to the preset target area, and obtain the spreader stability index of each grabbing control trajectory moving point in each grabbing control trajectory of the container gantry crane to be controlled to grab each type of each container to be stacked to the preset target area. ; and comprehensively analyze the arm length reference value, tilt angle reference value, cable torque reference value, cable deformation reference value of the container gantry crane to be controlled and the arm length value, tilt angle value, cable torque value, cable deformation value of each grabbing control trajectory moving point in each grabbing control trajectory between grabbing each type of each container to be stacked to the preset target area, and obtain the operation stability index of each grabbing control trajectory moving point in each grabbing control trajectory when the container gantry crane to be controlled grabs each type of each container to be stacked to the preset target area; and comprehensively analyze the spreader stability index and operation stability index of each grabbing control trajectory moving point in each grabbing control trajectory when the container gantry crane to be controlled grabs each type of each container to be stacked to the preset target area, and obtain the operation stability index of each grabbing control trajectory moving point in each grabbing control trajectory when the container gantry crane to be controlled grabs each type of each container to be stacked to the preset target area.

[0065] The reference value of the spreader acceleration of the container gantry crane to be controlled can be obtained through several historical spreader acceleration values, that is, a mean analysis is performed to obtain the spreader acceleration reference value.

[0066] The steps for obtaining the sling angular velocity reference value, sling vibration amplitude reference index, arm length reference value, tilt angle reference value, cable torque reference value, cable deformation reference value and sling acceleration reference value of the container gantry crane to be controlled are consistent.

[0067] The specific formula for calculating the spreader stability index and the operation stability index of each grab control trajectory moving point in each grab control trajectory for the container gantry crane to grab each type of each container to be stacked to the preset target area is as follows: Among them, DwZ ijmn The spreader stability index of the nth grab control trajectory moving point in the mth grab control trajectory for the container gantry crane to grab the jth container to be stacked of the i-th type to the preset target area, DsZ ijmn The acceleration value of the spreader at the moving point of the nth grabbing control trajectory in the mth grabbing control trajectory for the container gantry crane to grab the jth container to be stacked of the i-th type to the preset target area, DaZ ijmn The angular velocity value of the spreader at the moving point of the nth grabbing control trajectory in the mth grabbing control trajectory when the container gantry crane to be controlled grabs the jth container to be stacked of the i-th type to the preset target area, DzF ijmn is the spreader vibration amplitude index of the nth grabbing control trajectory moving point in the mth grabbing control trajectory for the container gantry crane to be controlled to grab the jth container to be stacked of the i-th type to the preset target area, CdS is the spreader acceleration reference value of the container gantry crane to be controlled, CaD is the spreader angular velocity reference value of the container gantry crane to be controlled, CzF is the spreader vibration amplitude reference index of the container gantry crane to be controlled, Φ1 is the acceleration coefficient stored in the database, Φ2 is the angular velocity coefficient stored in the database, Φ3 is the vibration amplitude coefficient stored in the database, δ1 is the acceleration adjustment coefficient stored in the database, δ2 is the angular velocity adjustment coefficient stored in the database, δ3 is the vibration amplitude adjustment coefficient stored in the database, Φ1+Φ2+Φ3=1, YxW ijmn is the operation stability index of the nth grab control trajectory moving point in the mth grab control trajectory for the container gantry crane to grab the jth container to be stacked of the i-th type to the preset target area, CzW ijmn is the operation stability index of the nth grabbing control trajectory moving point in the mth grabbing control trajectory for the container gantry crane to be controlled to grab the jth container to be stacked of the i-th type to the preset target area, λ1 is the spreader coefficient stored in the database, λ2 is the operation coefficient stored in the database, λ1+λ2=1, i=1,2,3,…,i0, i0 is the number of types, j=1,2,3,…,j0, j0 is the number of containers to be stacked, m=1,2,3,…,m0, m0 is the number of grabbing control trajectories, n=1,2,3,…,n0, n0 is the number of moving points of the grabbing control trajectory, and e is a natural constant, and in this implementation example, the value is 2.71.

[0068] It needs to be explained that the operation stability index of each moving point of each grabbing control trajectory in each grabbing control trajectory in which the container gantry crane to be controlled grabs each type of each container to be stacked to a preset target area is consistent with the calculation logic of the spreader stability index.

[0069] And Φ1, Φ2, and Φ3 can be obtained through the following steps: standardize the spreader acceleration reference value, spreader angular velocity reference value, and spreader vibration amplitude reference index of the controlled container gantry crane, perform sum analysis based on the standardized results to obtain the spreader stability sum value, and perform proportion analysis on the standardized results and the spreader stability sum value, and use the proportion analysis results as the corresponding coefficients.

[0070] δ1, δ2, and δ3 can be obtained through the following steps: First, based on historical data, the initial influence weight of each variable on the spreader stability index is determined through statistical regression analysis. Then, the range of coefficients is adjusted using the sensitivity analysis method to evaluate the stability and applicability of these parameters to the formula output. Next, the weights are further fitted through model optimization (such as multi-objective optimization) to ensure that the formula can accurately reflect the stability of the actual spreader.

[0071] λ1 and λ2 can be obtained through the following steps: perform mean analysis on the spreader stability index and operation stability index of each moving point of each grabbing control trajectory in which the container gantry crane to be controlled grabs each type of each container to be stacked to the preset target area, and obtain the mean value of the spreader stability index and the mean value of the operation stability index of the container gantry crane to be controlled, and perform sum analysis to obtain the operation stability sum value, perform proportion analysis on the mean value of the spreader stability index and the mean value of the operation stability index of the container gantry crane to be controlled, and use the proportion analysis results as the corresponding coefficients.

[0072] In this implementation scheme, through comprehensive analysis of the spreader stability index and the operation stability index, the stability of each moving point of the grab control trajectory can be accurately measured, and the overall operation stability of the spreader and the crane can be optimized. At the same time, it is ensured that during the grabbing process, the dynamic behavior of the crane's spreader, steel cable and other components does not fluctuate violently or become unstable, thereby improving the stability and safety of the overall operation. Secondly, the spreader stability index and the operation stability index are comprehensively analyzed to provide reliable data support and help the control system optimize the path of each moving point, thereby reducing unnecessary adjustments or repositioning, thereby improving the accuracy and efficiency of the operation, and ensuring that the stability of the crane is always in the best state under different operating conditions, avoiding dangerous events caused by unstable factors. Then, through data standardization, regression analysis, sensitivity analysis and other means, predictive analysis based on historical data can be realized, thereby promoting the intelligent adaptation and optimization of the system in different scenarios. Finally, this step can not only help evaluate the stability of the current path, but also provide more flexible adjustment space for path planning, thereby ensuring that each grab point is executed within an acceptable stability range, thereby improving the execution effect.

[0073] Specifically, the specific steps of taking trajectory control adjustment measures based on the operation stability index of each grabbing control trajectory moving point in each grabbing control trajectory in which the container gantry crane to be controlled grabs each container to be stacked of each type to a preset target area are as follows: the operation stability index of the first grabbing control trajectory moving point in each grabbing control trajectory in which the container gantry crane to be controlled grabs each container to be stacked of each type to a preset target area is compared and analyzed, and according to the analysis result, the corresponding moving trajectory of the first grabbing control trajectory moving point in which the container gantry crane to be controlled grabs each container to be stacked of each type to a preset target area is selected as the first optimal moving trajectory; when the container gantry crane to be controlled grabs each container to be stacked of each type to a preset target area, the moving trajectory of the first grabbing control trajectory moving point in which the container gantry crane to be controlled grabs each container to be stacked of each type to a preset target area is selected as the first optimal moving trajectory; After the stacked container is grabbed to the preset target area by the first optimal moving trajectory, a discriminant analysis is performed on the operation stability index of the second grabbing control trajectory moving point on the first optimal moving trajectory that the container gantry crane to be controlled grabs each type of each container to be stacked to the preset target area and the operation stability index of the second grabbing control trajectory moving point of each remaining moving trajectory, and according to the discriminant analysis, the corresponding moving trajectory of the second grabbing control trajectory moving point that the container gantry crane to be controlled grabs each type of each container to be stacked to the preset target area is selected as the second optimal moving trajectory; and the steps of discriminant analysis and selecting the optimal moving trajectory are repeated until the container gantry crane to be controlled grabs each type of each container to be stacked to the preset target area.

[0074] Among them, the discriminant analysis selects the container gantry crane to be controlled to grab each type of each container to be stacked to the preset target area. The corresponding movement trajectory of the second grab control trajectory movement point is as the second optimal movement trajectory: If the operating stability index of the second grabbing control trajectory moving point on the first optimal moving trajectory for the container gantry crane to be controlled to grab each type of container to be stacked to the preset target area is lower than the operating stability index of the second grabbing control trajectory moving point of each remaining moving trajectory, and combined with statistical analysis, the second optimal moving trajectory (i.e., the moving trajectory with the largest operating stability index) is obtained.

[0075] In this implementation scheme, the operation stability index of each moving point is discriminated and analyzed to gradually screen out the best trajectory, and the trajectory point with the highest stability is selected each time, so that the operation of the container gantry crane is more accurate and stable, while reducing the risk during the operation of the equipment. Secondly, the optimal trajectory point is selected through multiple comparisons and judgments to improve work efficiency, especially when containers need to be moved quickly and accurately. At the same time, the process is carried out dynamically, and further judgment and adjustment are made each time based on the optimization results of the previous step, so that the container gantry crane can respond to environmental changes and different states of containers in real time and maintain the optimal operating state. Finally, through statistical analysis and comparison, the impact of each step of selection is quantified, so that the entire decision-making process is more transparent and traceable, which is convenient for adjustment.

[0076] In summary, this application has at least the following effects: Through the container feature data recognition of the data acquisition and recognition module and the path planning of the image analysis and processing module, the accuracy of container grabbing and stacking is effectively improved, and the corresponding grabbing trajectory is generated, thereby improving the overall operation accuracy and work efficiency when facing different types or irregular containers, thereby improving the efficiency of the entire yard operation.

[0077] By running the real-time data collection and analysis of the analysis and processing module, the trajectory control status of the container gantry crane can be continuously monitored, especially real-time adjustments in complex operating environments, thereby reducing deviations in the operation process, and effectively ensuring the smooth operation of the container crane in various environments, thereby reducing scheduling delays and downtime, thereby improving operational stability and safety.

[0078] Through the integrated data acquisition and recognition module, image analysis and processing module, and trajectory control and adjustment module, different types of containers can be accurately identified, and an optimized grabbing path can be generated based on the recognition results. The stability of the operation trajectory can be adjusted based on real-time analysis to ensure that the consistency and accuracy of the operation are significantly enhanced, thereby reducing the risk of problems during the operation and improving operational efficiency.

[0079] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0080] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An automated container gantry crane control system, characterized in that: include: Data acquisition and recognition module, image analysis and processing module, operation analysis and processing module, trajectory control and adjustment module; The data acquisition and identification module is used to acquire characteristic data of a plurality of containers to be stacked when stacking the containers, and to perform identification and analysis to obtain a plurality of containers to be stacked of a plurality of types; The image analysis and processing module is used to obtain image data between the container gantry crane to be controlled grabbing each container to be stacked of each type and the preset target area, and perform image analysis to obtain a plurality of grab control trajectories between the container gantry crane to be controlled grabbing each container to be stacked of each type and the preset target area; The operation analysis and processing module is used to obtain in real time the operation status data of each grabbing control track moving point in each grabbing control track between each type of container to be stacked and a preset target area by the container gantry crane to be controlled, and perform data analysis to obtain the operation stability index of each grabbing control track moving point in each grabbing control track between each type of container to be stacked and a preset target area by the container gantry crane to be controlled; The trajectory control adjustment module is used to take trajectory control adjustment measures based on the operation stability index of each grabbing control trajectory moving point in each grabbing control trajectory for the container gantry crane to grab each type of each container to be stacked to a preset target area.

2. The automated container gantry crane control system according to claim 1, characterized in that: The characteristic data includes the aspect ratio, the height-to-width ratio, the volume value, and the weight value; the image data specifically includes the pixel value and two-dimensional coordinates of each pixel point; the operating status data includes the sling acceleration value, the sling angular velocity value, the sling vibration amplitude index, the arm length value, the inclination angle value, the steel cable torque value, and the steel cable deformation value.

3. The automated container gantry crane control system according to claim 2, characterized in that: The specific steps of obtaining several types of containers to be stacked are as follows: Normalize the length-to-width ratio, height-to-width ratio, volume value, and weight value of each container to be stacked; Comprehensively analyze the normalized length-to-width ratio, height-to-width ratio, volume value, and weight value of each container to be stacked to obtain a characteristic index of each container to be stacked; The characteristic index of each container to be stacked is judged and analyzed with a preset characteristic index threshold interval to obtain a plurality of containers to be stacked of a plurality of types.

4. The automated container gantry crane control system according to claim 2, characterized in that: The specific steps of obtaining a plurality of grab control trajectories for the container gantry crane to be controlled to grab each type of each container to be stacked to a preset target area are as follows: Inputting the pixel value of each pixel point between each type of container to be stacked grabbed by the container gantry crane to be controlled and the preset target area into the pre-trained recognition model for recognition processing, and obtaining several obstacle areas between each type of container to be stacked grabbed by the container gantry crane to be controlled and the preset target area; Performing median analysis on the two-dimensional coordinates of each obstacle pixel point in each obstacle area between the preset target areas when the container gantry crane to be controlled grabs each container to be stacked of each type, to obtain the two-dimensional coordinates of each obstacle area between the preset target areas when the container gantry crane to be controlled grabs each container to be stacked of each type, and performing coordinate conversion processing to obtain the three-dimensional position coordinates of the obstacles when the container gantry crane to be controlled grabs each container to be stacked of each type to each obstacle area between the preset target areas; Obtaining the lifting three-dimensional position coordinates of the container gantry crane to be controlled and the target three-dimensional position coordinates of the preset target area of ​​each type of each container to be stacked, and performing interpolation analysis to obtain the three-dimensional position coordinates of several potential moving points between the container gantry crane to be controlled to grab each type of each container to be stacked and the preset target area; Comprehensively analyze the lifting three-dimensional position coordinates of each potential moving point between each type of container to be stacked and the preset target area by the container gantry crane to be controlled, the obstacle three-dimensional position coordinates of each obstacle area and the preset safe moving distance of the container gantry crane, and obtain the reliability index of each potential moving point between each type of container to be stacked and the preset target area by the container gantry crane to be controlled; The reliability index of each potential moving point between the container gantry crane to be controlled and each container to be stacked of each type is comprehensively analyzed to obtain several grabbing control trajectories between the container gantry crane to be controlled and each container to be stacked of each type is grabbed and the preset target area.

5. The automated container gantry crane control system according to claim 4, characterized in that: The recognition model is specifically a convolutional neural network model, which includes an input layer, a convolutional layer, an activation layer, a pooling layer, a fully connected layer, and an output layer. The specific steps of obtaining the container gantry crane to be controlled to grab each type of container to be stacked to several obstacle areas between the preset target areas are as follows: In the input layer of the convolutional neural network model, the pixel value of each pixel point between each type of container to be stacked and the preset target area is received by the container gantry crane to be controlled; In the convolution layer of the convolutional neural network model, feature extraction processing is performed on the pixel value of each pixel point between the controlled container gantry crane grabbing each type of container to be stacked and the preset target area, so as to obtain a feature map between the controlled container gantry crane grabbing each type of container to be stacked and the preset target area; In the activation layer of the convolutional neural network model, a nonlinear transformation is performed on the feature map between each type of container to be stacked and the preset target area grabbed by the controlled container gantry crane; In the pooling layer of the convolutional neural network model, a dimension reduction process is performed on a feature map of each type of container to be stacked that is grasped by the controlled container gantry crane and placed in a preset target area after nonlinear transformation processing, so as to obtain a dimension reduction feature map of each type of container to be stacked that is grasped by the controlled container gantry crane and placed in a preset target area; In the fully connected layer of the convolutional neural network model, the dimension reduction feature map between each type of container to be stacked and the preset target area of ​​the controlled container gantry crane is flattened; In the output layer of the convolutional neural network model, contour recognition analysis is performed on the dimensionality reduction feature map after flattening, in which the controlled container gantry crane grabs each type of container to be stacked to several obstacle areas between the preset target areas, and the controlled container gantry crane grabs each type of container to be stacked to several obstacle areas between the preset target areas.

6. The automated container gantry crane control system according to claim 4, characterized in that: The specific formula for calculating the reliability index of each potential moving point between the container gantry crane to be controlled to grab each type of each container to be stacked to the preset target area is as follows: ； Among them, KxZ ijg is the reliability index of the container gantry crane to be controlled to grab the jth container to be stacked of the i-th type to the g-th potential moving point between the preset target area, (Xw ijg , Y ijg , Zw ijg ) is the lifting three-dimensional position coordinate of the g-th potential moving point between the container gantry crane to grab the j-th container to be stacked of the i-th type and the preset target area, (Xq ijh , Yq ijh , Zq ijh ) is the obstacle 3D position coordinate of the h-th obstacle area between the container gantry crane to be controlled to grab the j-th container to be stacked of the ith type and the preset target area, AyL is the preset safe moving distance of the container gantry crane, i=1,2,3,…,i0, i0 is the number of types, j=1,2,3,…,j0, j0 is the number of containers to be stacked, g=1,2,3,…,g0, g0 is the number of potential moving points, and h=1,2,3,…,h0, h0 is the number of obstacle areas.

7. The automated container gantry crane control system according to claim 4, characterized in that: The specific steps of comprehensively analyzing the reliability index of each potential moving point between each type of container to be stacked and the preset target area for the container gantry crane to be controlled are as follows: Comparing and analyzing the reliability index of each potential moving point between the container gantry crane to be controlled grabbing each type of each container to be stacked to the preset target area with the preset reliability index threshold value; If the reliability index of each potential moving point between the container gantry crane to be controlled grabbing each type of container to be stacked and the preset target area is lower than or equal to the preset reliability index threshold, the potential moving point is not marked; If the reliability index of each potential moving point between the container gantry crane to be controlled grabbing each container to be stacked of each type and the preset target area is higher than the preset reliability index threshold, the potential moving point is marked as a grab control trajectory moving point, and statistical analysis is performed to obtain a number of grab control trajectory moving points between the container gantry crane to be controlled grabbing each container to be stacked of each type and the preset target area; And each moving point of the grabbing control trajectory between the container gantry crane to be controlled grabbing each container to be stacked of each type and the preset target area is smoothed to obtain a plurality of grabbing control trajectories between the container gantry crane to be controlled grabbing each container to be stacked of each type and the preset target area.

8. The automated container gantry crane control system according to claim 2, characterized in that: The specific steps of obtaining the operation stability index of each moving point of each grabbing control trajectory in each grabbing control trajectory in which the container gantry crane to be controlled grabs each type of each container to be stacked to a preset target area are as follows: Obtain a reference value of the spreader acceleration, a reference value of the spreader angular velocity, a reference index of the spreader vibration amplitude, a reference value of the arm length, a reference value of the tilt angle, a reference value of the steel cable torque, and a reference value of the steel cable deformation of the container gantry crane to be controlled; Comprehensively analyze the spreader acceleration reference value, spreader angular velocity reference value, spreader vibration amplitude reference index of the container gantry crane to be controlled and the spreader acceleration value, spreader angular velocity value, spreader vibration amplitude index of each grabbing control trajectory moving point in each grabbing control trajectory between grabbing each type of each container to be stacked to a preset target area, and obtain the spreader stability index of each grabbing control trajectory moving point in each grabbing control trajectory between grabbing each type of each container to be stacked to a preset target area by the container gantry crane to be controlled; A comprehensive analysis is performed on the arm length reference value, tilt angle reference value, cable torque reference value, cable deformation reference value of the container gantry crane to be controlled and the arm length value, tilt angle value, cable torque value, cable deformation value of each grabbing control trajectory moving point in each grabbing control trajectory between grabbing each type of each container to be stacked to a preset target area, to obtain an operation stability index of each grabbing control trajectory moving point in each grabbing control trajectory for the container gantry crane to be controlled to grab each type of each container to be stacked to a preset target area; The hoisting equipment stability index and operation stability index of each grabbing control trajectory moving point in each grabbing control trajectory in which the container gantry crane to be controlled grabs each type of container to be stacked to the preset target area are comprehensively analyzed to obtain the operation stability index of each grabbing control trajectory moving point in each grabbing control trajectory in which the container gantry crane to be controlled grabs each type of container to be stacked to the preset target area.

9. The automated container gantry crane control system according to claim 8, characterized in that: The specific formula for calculating the spreader stability index and the operation stability index of each grab control trajectory moving point in each grab control trajectory for the container gantry crane to grab each type of each container to be stacked to the preset target area is as follows: ； Among them, DwZ ijmn The spreader stability index of the nth grab control trajectory moving point in the mth grab control trajectory for the container gantry crane to grab the jth container to be stacked of the i-th type to the preset target area, DsZ ijmn 、DaZ ijmn ,DzF ijmn are the spreader acceleration value, spreader angular velocity value, and spreader vibration amplitude index of the nth grabbing control trajectory moving point in the mth grabbing control trajectory when the container gantry crane to be controlled grabs the jth container to be stacked of the i-th type to the preset target area. CdS, CaD, and CzF are the spreader acceleration reference value, spreader angular velocity reference value, and spreader vibration amplitude reference index of the container gantry crane to be controlled, respectively. They are the acceleration coefficient, angular velocity coefficient, and vibration amplitude coefficient stored in the database, They are the acceleration adjustment coefficient, angular velocity adjustment coefficient, and vibration amplitude adjustment coefficient stored in the database. ,YxW ijmn is the operation stability index of the nth grab control trajectory moving point in the mth grab control trajectory for the container gantry crane to grab the jth container to be stacked of the i-th type to the preset target area, CzW ijmn is the operational stability index of the nth grabbing control trajectory moving point in the mth grabbing control trajectory for the container gantry crane to grab the jth container to be stacked of the i-th type to the preset target area, They are the spreader coefficient and operation coefficient stored in the database, , i=1,2,3,…,i0, i0 is the number of types, j=1,2,3,…,j0, j0 is the number of containers to be stacked, m=1,2,3,…,m0, m0 is the number of grasping control trajectories, n=1,2,3,…,n0, n0 is the number of moving points of the grasping control trajectory, and e is a natural constant.

10. The automated container gantry crane control system according to claim 1, characterized in that: The specific steps of taking trajectory control adjustment measures based on the operation stability index of each grabbing control trajectory moving point in each grabbing control trajectory in which the container gantry crane to be controlled grabs each type of container to be stacked to a preset target area are as follows: Comparing and analyzing the operation stability index of the first grabbing control trajectory moving point in each grabbing control trajectory in which the container gantry crane to be controlled grabs each type of container to be stacked to a preset target area, and selecting the corresponding moving trajectory of the first grabbing control trajectory moving point in which the container gantry crane to be controlled grabs each type of container to be stacked to a preset target area as the first optimal moving trajectory according to the analysis result; After the container gantry crane to be controlled grabs each container to be stacked of each type to a preset target area along a first optimal moving trajectory, a discriminant analysis is performed on an operation stability index of a second grabbing control trajectory moving point on the first optimal moving trajectory for grabbing each container to be stacked of each type to a preset target area by the container gantry crane to be controlled and an operation stability index of a second grabbing control trajectory moving point on each remaining moving trajectory, and a corresponding moving trajectory of a second grabbing control trajectory moving point for grabbing each container to be stacked of each type by the container gantry crane to be controlled to a preset target area is selected as a second optimal moving trajectory according to the discriminant analysis; The steps of discriminant analysis and selecting the optimal moving trajectory are repeated until the container gantry crane to be controlled grabs each type of container to be stacked to a preset target area.

Images